A Stereo Algorithm for Thin Obstacles and Reflective Objects

Stereo cameras are a popular choice for obstacle avoidance for outdoor lighweight, low-cost robotics applications. However, they are unable to sense thin and reflective objects well. Currently, many algorithms are tuned to perform well on indoor scenes like the Middlebury dataset. When navigating outdoors, reflective objects, like windows and glass, and thin obstacles, like wires, are not well handled by most stereo disparity algorithms. Reflections, repeating patterns and objects parallel to the cameras' baseline causes mismatches between image pairs which leads to bad disparity estimates. Thin obstacles are difficult for many sliding window based disparity methods to detect because they do not take up large portions of the pixels in the sliding window. We use a trinocular camera setup and micropolarizer camera capable of detecting reflective objects to overcome these issues. We present a hierarchical disparity algorithm that reduces noise, separately identify wires using semantic object triangulation in three images, and use information about the polarization of light to estimate the disparity of reflective objects. We evaluate our approach on outdoor data that we collected. Our method contained an average of 9.27% of bad pixels compared to a typical stereo algorithm's 18.4% of bad pixels in scenes containing reflective objects. Our trinocular and semantic wire disparity methods detected 53% of wire pixels, whereas a typical two camera stereo algorithm detected 5%.

[1]  Sebastian Scherer,et al.  Wire detection using synthetic data and dilated convolutional networks for unmanned aerial vehicles , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Ruigang Yang,et al.  Semantic Segmentation of Urban Scenes Using Dense Depth Maps , 2010, ECCV.

[3]  Maarten Vergauwen,et al.  A Hierarchical Symmetric Stereo Algorithm Using Dynamic Programming , 2002, International Journal of Computer Vision.

[4]  Toshio Ueshiba An Efficient Implementation Technique of Bidirectional Matching for Real-time Trinocular Stereo Vision , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[5]  Jiaolong Yang,et al.  Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Takeo Kanade,et al.  A Multiple-Baseline Stereo , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Mikhail Sizintsev Hierarchical Stereo with Thin Structures and Transparency , 2008, 2008 Canadian Conference on Computer and Robot Vision.

[8]  Roberto Cipolla,et al.  Segmentation and Recognition Using Structure from Motion Point Clouds , 2008, ECCV.

[9]  Marc Pollefeys,et al.  Real-time stereo matching failure prediction and resolution using orthogonal stereo setups , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Martin Humenberger,et al.  A census-based stereo vision algorithm using modified Semi-Global Matching and plane fitting to improve matching quality , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[11]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Peter Pirsch,et al.  Evaluation of Penalty Functions for Semi-Global Matching Cost Aggregation , 2012 .

[13]  Heiko Hirschmüller,et al.  Stereo Processing by Semiglobal Matching and Mutual Information , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Maziar Loghman,et al.  SGM-based dense disparity estimation using adaptive Census transform , 2013, 2013 International Conference on Connected Vehicles and Expo (ICCVE).

[15]  Lutz Falkenhagen Hierarchical Block-Based Disparity Estimation Considering Neighbourhood Constraints , 1997 .

[16]  Larry H. Matthies,et al.  Depth from stereo polarization in specular scenes for urban robotics , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Andrew W. Fitzgibbon,et al.  Reflection Modeling for Passive Stereo , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[18]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1999, International Journal of Computer Vision.